Developing story · 2 episodes · 22 Sept to 2 Oct
Advancing Legal NER Through On-Device Optimization
Researchers have advanced Named Entity Recognition capabilities by releasing a specialized dataset for international law and subsequently comparing on-device models for efficiency. The saga currently stands at a point where the focus has shifted from data creation to optimizing model performance for local deployment.
-
Study compares On-Device NER models for speed, cost and accuracy
A new arXiv paper tests nine named-entity recognition systems for on-device use, where latency and data privacy matter more than leaderboard scores. They evaluate accuracy, latency (milliseconds to…
1 source primary source -
Researchers release IntLawNER dataset for international law NER
The paper introduces IntLawNER, a new named‑entity‑recognition dataset covering 2,987 gold‑annotated sentences and 8,094 entity spans drawn from International Court of Justice decisions, UN Security…
1 source primary source
Who and what